2
Swarm Intelligence Applications in Electric
Machines
Amr M. Amin and Omar T. Hegazy
Power and Electrical Machines Department, Faculty of Engineering – Helwan University
Egypt
1. Introduction
Particle Swarm Optimization (PSO) has potential applications in electric drives. The
excellent characteristics of PSO may be successfully used to optimize the performance of
electric machines in many aspects.
In this chapter, a field-oriented controller that is based on Particle Swarm Optimization is
presented. In this system, the speed control of two asymmetrical windings induction motor
is achieved while maintaining maximum efficiency of the motor. PSO selects the optimal
rotor flux level at any operating point. In addition, the electromagnetic torque is also
improved while maintaining a fast dynamic response. A novel approach is used to evaluate
the optimal rotor flux level by using Particle Swarm Optimization. PSO method is a
member of the wide category of Swarm Intelligence methods (SI). There are two speed
control strategies will demonstrate in next sections. These are field-oriented controller
(FOC), and FOC based on PSO. The strategies are implemented mathematically and
experimental. The simulation and experimental results have demonstrated that the FOC
based on PSO method saves more energy than the conventional FOC method.
In this chapter, another application of PSO for losses and operating cost minimization
control is presented for the induction motor drives. Two strategies for induction motor
speed control are proposed in this section. These strategies are based on PSO and called
maximum efficiency strategy and minimum operating cost Strategy. The proposed
technique is based on the principle that the flux level in a machine can be adjusted to give
the minimum amount of losses and minimum operating cost for a given value of speed and
load torque.
In the demonstrated systems, the flux and torque hysteresis bands are the only adjustable
parameters to achieve direct torque control (DTC) of induction motors. Their selection
greatly influences the inverter switching loss, motor harmonic loss and motor torque
ripples, which are the major performance criteria. In this section, the effects of flux and
torque hysteresis bands are investigated and optimized by the particle swarms optimization
technique. A DTC control strategy with variable hysteresis bands, which improves the
drive performance compared to the classical DTC, is presented.
Online Artificial Neural Networks (ANNs) could be also trained based on PSO optimized
data. Here the fast response of ANN is used to optimize the operating conditions of the
machine.